youtube-script-writer
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No instances of prompt injection, obfuscation, or unauthorized access to sensitive files were detected within the skill instructions. The functionality aligns with the stated purpose of generating video scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external sources via web search tools, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: External research material and URLs are gathered using WebSearch/WebFetch as specified in the 'Inputs to gather first' section.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded in the fetched research data.
- Capability inventory: The skill is limited to generating text for video scripts; it does not request or use capabilities for file system writes, network exfiltration, or command execution.
- Sanitization: There are no explicit instructions to sanitize or validate the content retrieved from external URLs before processing.
Audit Metadata